Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 144 718 707 319 752 907 594 678 601 766 645 267 366 250 142 441 195 942 345 346
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 142 707 250 195 319 601 594 718 346 267  NA 907 942 752 441 345 678 766 366  NA 144 645  NA
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 4 5 4 5 2 5 4 4 5 5
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y"
[26] "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y"
[26] "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "b" "o" "r" "j" "y" "B" "A" "M" "Y" "U"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  6 18
which( manyNumbersWithNA > 900 )
[1] 12 13
which( is.na( manyNumbersWithNA ) )
[1] 11 20 23

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 907 942
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 907 942
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 907 942

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "B" "A" "M" "Y" "U"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "b" "o" "r" "j" "y"
manyNumbers %in% 300:600
 [1] FALSE FALSE FALSE  TRUE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE  TRUE
[17] FALSE FALSE  TRUE  TRUE
which( manyNumbers %in% 300:600 )
[1]  4  7 13 16 19 20
sum( manyNumbers %in% 300:600 )
[1] 6

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" "large" "small" "small" "small" "large" "large" "large" "small" "small" NA      "large"
[13] "large" "large" "small" "small" "large" "large" "small" NA      "small" "large" NA     
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "large"   "small"   "small"   "small"   "large"   "large"   "large"   "small"   "small"  
[11] "UNKNOWN" "large"   "large"   "large"   "small"   "small"   "large"   "large"   "small"   "UNKNOWN"
[21] "small"   "large"   "UNKNOWN"
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0 707   0   0   0 601 594 718   0   0  NA 907 942 752   0   0 678 766   0  NA   0 645  NA

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 4 5 2
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  4  5  2
duplicated( duplicatedNumbers )
 [1] FALSE FALSE  TRUE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 13
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 942
which.min( manyNumbersWithNA )
[1] 1
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 142
range( manyNumbersWithNA, na.rm = TRUE )
[1] 142 942

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 142 707 250 195 319 601 594 718 346 267  NA 907 942 752 441 345 678 766 366  NA 144 645  NA
sort( manyNumbersWithNA )
 [1] 142 144 195 250 267 319 345 346 366 441 594 601 645 678 707 718 752 766 907 942
sort( manyNumbersWithNA, na.last = TRUE )
 [1] 142 144 195 250 267 319 345 346 366 441 594 601 645 678 707 718 752 766 907 942  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 942 907 766 752 718 707 678 645 601 594 441 366 346 345 319 267 250 195 144 142  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 142 707 250 195 319
order( manyNumbersWithNA[1:5] )
[1] 1 4 3 5 2
rank( manyNumbersWithNA[1:5] )
[1] 1 5 3 2 4
sort( mixedLetters )
 [1] "A" "b" "B" "j" "M" "o" "r" "U" "y" "Y"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 1.5 9.5 7.0 1.5 7.0 7.0 9.5 4.0 4.0 4.0
rank( manyDuplicates, ties.method = "min" )
 [1] 1 9 6 1 6 6 9 3 3 3
rank( manyDuplicates, ties.method = "random" )
 [1]  2  9  8  1  7  6 10  5  3  4

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.0000000 -0.5000000  0.0000000  0.5000000  1.0000000 -0.9078785 -0.6060720  0.6615491 -0.5084113
[10]  1.4067294  0.2325062 -0.4072786 -1.4699789 -1.9084736 -0.5102904
round( v, 0 )
 [1] -1  0  0  0  1 -1 -1  1 -1  1  0  0 -1 -2 -1
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -0.9 -0.6  0.7 -0.5  1.4  0.2 -0.4 -1.5 -1.9 -0.5
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -0.91 -0.61  0.66 -0.51  1.41  0.23 -0.41 -1.47 -1.91 -0.51
floor( v )
 [1] -1 -1  0  0  1 -1 -1  0 -1  1  0 -1 -2 -2 -1
ceiling( v )
 [1] -1  0  0  1  1  0  0  1  0  2  1  0 -1 -1  0

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2023 Biomedical Data Sciences (BDS) | LUMC